DESC:FORM 2 THE PATENTS ACT, 1970 (39 of 1970) & THE PATENT RULES, 2003 COMPLETE SPECIFICATION (See Section 10 and Rule 13) Title of invention: METHOD AND SYSTEM FOR OPTIMIZATION OF AGGLOMERATION OF ORES Applicant: Tata Consultancy Services Limited A company Incorporated in India under the Companies Act, 1956 Having address: Nirmal Building, 9th Floor, Nariman Point, Mumbai 400021, Maharashtra, India The following specification particularly describes the invention and the manner in which it is to be performed. CROSS-REFERENCE TO RELATED APPLICATIONS AND PRIORITY The present application claims priority from Indian provisional application no. 201921026929, filed on July 04, 2019. The entire contents of the aforementioned application are incorporated herein by reference. TECHNICAL FIELD The disclosure herein generally relates to the field of ore agglomeration, and, more particularly, to a method and system for optimization of agglomeration processes such as sintering and pelletization that are used for agglomerating ores of metals such as iron ore, zinc ore, manganese ore, etc. in an agglomeration plant. BACKGROUND During mining operations, mechanized mining of ores generates a large percentage of fine particles that cannot be directly utilized for extraction of metallic content. The fine particles need to be increased in size using appropriate agglomeration processes to yield agglomerates that can then be utilized in furnaces such as blast furnaces, submerged arc furnaces, rotary kilns, etc. for extraction of metallic content from the ores. Sintering and pelletization are two widely used agglomeration processes that involve blending/mixing of ore fines along with fluxes, fuel and other additives to yield input feed mix, wet agglomeration of the input feed mix via granulating or balling to yield wet agglomerate (green mix or green balls), charging and subjecting the wet agglomerate to thermal agglomeration to yield fired agglomerates such as sinter or pellets, and cooling and sizing of the agglomerates. Blending/mixing may be carried out using stackers and reclaimers, mixing drums, high intensity mixers, etc. Wet agglomeration may be carried out in granulation/balling discs and drums. Thermal agglomeration may be carried out in moving/static thermal agglomeration devices such as horizontal moving grate/strand, rotary kiln, vertical shaft kiln, etc. The quality of agglomerates obtained from the agglomeration processes strongly influences the efficacy of the subsequent metal extraction processes. The quality and yield of agglomerates in turn depends on various factors such as size distribution and chemical composition of individual feed materials, output of blending operation (size distribution, chemical composition and moisture content of feed mix), output of wet agglomeration operation (particle size distribution, moisture content and composition of green mix/balls), thermal agglomeration process operating conditions (strand speed, firing temperature, furnace pressure, etc.) and external factors such as ambient temperature. Agglomeration processes are quite sensitive to the input feed material characteristics such as composition, size distribution and density. Typically, these characteristics varies widely and frequently, thereby affecting the yield and productivity of the process, agglomerate quality and stability of the plant making it difficult for the agglomeration plant to operate at its optimum level. Thus, end-to-end process monitoring and optimization of all the units involved in agglomeration is crucial to attain maximum plant efficacy. Additionally, lack of real-time measurement of key process parameters such as agglomerate quality and composition, productivity, particle size distribution (PSD) of wet agglomerates, and green bed permeability or voidage due to sampling constraints, absence of instruments and long laboratory test times makes it difficult to track the process behavior in real-time. Lack of such critical information makes it difficult to optimize the key parameters like productivity, product quality, energy consumption, percentage uptime, etc. There have been some efforts to apply data analytics, process monitoring and process optimization to agglomeration processes. Various efforts have been made to model the wet agglomeration and thermal agglomeration processes individually. For the thermal agglomeration process, physics-based models ranging from basic 1-D models to detailed 3-D models have been developed. SUMMARY Embodiments of the present disclosure present technological improvements as solutions to one or more of the above-mentioned technical problems recognized by the inventors in conventional systems. For example, in one embodiment, a system for optimizing the operation of an agglomeration plant is provided. The system comprises an input/output interface, a memory and one or more hardware processors. The input/output interface receives a plurality of data as an input from one or more data sources of the agglomeration plant at a pre-determined frequency, wherein the plurality of data comprises of a real-time and non-real-time data. The memory in communication with the one or more hardware processors, wherein the one or more first hardware processors are configured to execute programmed instructions stored in the one or more first memories, to: preprocess the plurality of data; obtain simulated data using the preprocessed data and a plurality of soft sensors, wherein the simulated data is integrated with preprocessed data to obtain integrated data; determine a first set of parameters using a physics-based wet agglomeration model and the integrated data; determine a second set of parameters using physics-based and data-driven charging models, the first set of parameters and the integrated data; determine a third set of parameters using a physics-based thermal agglomeration model, the first set of parameters, the second set of parameters and the integrated data; determine a final set of parameters using a plurality of data-driven models, the first, the second and the third set of parameters, and the integrated data; configure an optimizer using the plurality of physics-based and data-driven models of the agglomeration plant to optimize a plurality of key performance parameters of the agglomeration plant; generate at least one recommendation using the configured optimizer, wherein the recommendations comprise of optimal settings of a plurality of manipulated variables; and provide the generated recommendations to optimize the key performance parameters of the agglomeration plant. In another aspect, a method for optimizing the operation of an agglomeration plant is provided. Initially, a plurality of data is received as an input from one or more data sources of the agglomeration plant at a predetermined frequency, wherein the plurality of data comprises of a real-time and non-real-time data. The plurality of data is then preprocessed. Further, simulated data is obtained using the preprocessed data and a plurality of soft sensors, wherein the simulated data is integrated with preprocessed data to obtain integrated data. In the next step, a first set of parameters is determined using a physics-based wet agglomeration model and the integrated data. Further, a second set of parameters is determined using physics-based and data-driven charging models, the first set of parameters and the integrated data. In the next step, a third set of parameters is determined using a physics-based thermal agglomeration model, the first set of parameters, the second set of parameters and the integrated data. Further, a final set of parameters is determined using a plurality of data-driven models, the first, the second and the third set of parameters, and the integrated data. In the next step, an optimizer is configured using the plurality of physics-based and data-driven models of the agglomeration plant to optimize a plurality of key performance parameters of the agglomeration plant. Later, at least one recommendation is generated using the configured optimizer, wherein the recommendations comprise of optimal settings of a plurality of manipulated variables. And finally, the generated recommendations are provided to optimize the key performance parameters of the agglomeration plant. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed. BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles: FIG. 1 is a block diagram of the system for optimizing the operation of an agglomeration plant according to an embodiment of the present disclosure. FIG. 2 is a network diagram of the system for optimizing the operation of an agglomeration plant according to some embodiments of the present disclosure. FIG. 3 illustrates a process flow diagram of the agglomeration process in an ore sintering plant shown FIG. 2 according to an embodiment of the present disclosure. FIG. 4 is a block diagram of a prediction module of the system of FIG. 1 according to an embodiment of the present disclosure. FIG. 5 is a block diagram of an optimization module of the system of FIG. 1 according to an embodiment of the present disclosure. FIG. 6 is a block diagram of a self-learning module of the system of FIG. 1 according to an embodiment of the present disclosure. FIG. 7A-7B shows a flowchart illustrating the steps involved in optimizing the operation of the agglomeration plant according to an embodiment of the present disclosure. FIG. 8 is the graphical representation of the temperature profiles obtained from the thermal agglomeration model according to an embodiment of the present disclosure. FIG. 9 is graphical representation of sample optimization recommendations in the form of a Pareto chart according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF EMBODIMENTS Exemplary embodiments are described with reference to the accompanying drawings. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the scope of the disclosed embodiments. It is intended that the following detailed description be considered as exemplary only, with the true scope being indicated by the following claims. Agglomeration process in agglomeration plants are quite sensitive to the input feed material characteristics such as chemical composition, microstructure, size distribution and density. Typically, these characteristics varies widely and frequently, thereby affecting the yield and productivity of the process, agglomerate quality and stability of the plant making it difficult for the agglomeration plant to operate at its optimum level. Additionally, lack of real-time measurement of key process parameters such as agglomerate quality and composition, productivity, particle size distribution of wet agglomerates, and green bed permeability and voidage due to sampling constraints, absence of instruments and long laboratory test times makes it difficult to track the process behavior in real-time. Lack of such critical information makes it difficult to optimize the key parameters like productivity, product quality, energy consumption, percentage uptime, etc. Process optimization of the thermal agglomeration unit for maximizing the productivity while maintaining the fired agglomerate quality has been explored. However, end-to-end optimization of the agglomerate process by combing all the units involved has not been attempted, possibly due to unique complexities and challenges associated with combining the individual process outputs. Thus the present disclosure provides a method and system for optimizing the operation of an agglomeration plant. The system performs end-to-end real time optimization on integrated thermal agglomeration and wet agglomeration process which subsequently increases the process productivity and minimizes the operating cost and emissions while maintaining the output product quality. The optimization process involves various steps such as receiving data, pre-processing of data, prediction using physics-based and data-driven models of the agglomeration plant, and optimization configuration and execution. The process also involves continuous monitoring of model performance and self-learning of the models in case of drift. The system is also configured to estimate the key performance indicators (KPIs) of the agglomeration plant such as particle size distribution of wet agglomerates, bed permeability, temperature profile of the thermal agglomeration unit, plant productivity, fuel consumption and product quality in real-time. The system is also configured to provide a model-based multi-objective constrained optimization framework to optimize the key performance indicators of the agglomeration plant. Referring now to the drawings, and more particularly to FIG. 1 through FIG. 9, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments and these embodiments are described in the context of the following exemplary system and/or method. According to an embodiment of the disclosure, a block diagram of a system 100 for optimization the operation of an agglomeration plant 102 is shown in FIG. 1. The agglomeration plant 102 comprises wet agglomeration, charging device and thermal agglomeration process of ores such as iron ore, zinc ore, manganese ore and lead ore. The system 100 can be used for real-time optimization of the wet agglomeration unit, the thermal agglomeration unit or the entire agglomeration plant. According to an embodiment of the disclosure, the system 100 includes a physics-based models of the wet agglomeration unit and the thermal agglomeration unit. These models are developed considering all possible macro or micro processes of all species taking place in the units, and are tuned and validated with historical data from the agglomeration plant. In addition, the system 100 also includes data-based models for key process parameters and soft sensors of the agglomeration plant. These models are trained and validated using historical data of the agglomeration plant. According to an embodiment of the disclosure, a network diagram (architectural view) of the system 100 for optimization of the agglomeration plant 102 is shown in FIG 2. It may be understood that the system 100 may comprises one or more computing devices 104, such as a laptop computer, a desktop computer, a notebook, a workstation, a cloud-based computing environment and the like. It will be understood that the system 100 may be accessed through one or more input/output interfaces 106-1, 106-2... 106-N, collectively referred to as I/O interface 106. Examples of the I/O interface 106 may include, but are not limited to, a user interface, a portable computer, a personal digital assistant, a handheld device, a smartphone, a tablet computer, a workstation and the like. The I/O interface 106 are communicatively coupled to the system 100 through a network 108. In an embodiment, the network 108 may be a wireless or a wired network, or a combination thereof. In an example, the network 108 can be implemented as a computer network, as one of the different types of networks, such as virtual private network (VPN), intranet, local area network (LAN), wide area network (WAN), the internet, and such. The network 108 may either be a dedicated network or a shared network, which represents an association of the different types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), and Wireless Application Protocol (WAP), to communicate with each other. Further, the network 108 may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices. The network devices within the network 108 may interact with the system 100 through communication links. In an embodiment, the computing device 104 further comprises one or more hardware processors 110, hereinafter referred as a processor 110, one or more memory 112, hereinafter referred as a memory 112 and a data repository 114 or a database 114, for example, a repository 114. The memory 112 is in communication with the one or more hardware processors 110, wherein the one or more hardware processors 110 are configured to execute programmed instructions stored in the memory 112, to perform various functions as explained in the later part of the disclosure. The repository 114 may store data processed, received, and generated by the system 100. The system 110 supports various connectivity options such as BLUETOOTH®, USB, ZigBee and other cellular services. The network environment enables connection of various components of the system 110 using any communication link including Internet, WAN, MAN, and so on. In an exemplary embodiment, the system 100 is implemented to operate as a stand-alone device. In another embodiment, the system 100 may be implemented to work as a loosely coupled device to a smart computing environment. The components and functionalities of the system 110 are described further in detail. According to an embodiment of the disclosure, FIG. 3 illustrates a process flow diagram of the agglomeration process in the agglomeration plant 102. In an example, the agglomeration plant 102 is an iron ore sintering plant. Input raw materials consisting of iron ore fines (< 10 mm in size), fluxes (< 3 mm in size), solid fuel (< 3 mm in size), undersized agglomerate fines (known as return fines) and iron bearing wastes from other processing units in the metal extraction industry are blended in predetermined proportions in such a way that the chemical composition of the agglomerate meets specified thresholds. Fluxes are used to provide chemical species such as CaO and MgO required for the subsequent metal extraction process. Solid fuel is used to provide thermal energy required for the agglomeration process. Undersized agglomerate fines and iron bearing wastes are recycled via the agglomeration plant. The blended raw materials, typically known as base mix, are typically layered into a stockpile 116. The base mix from the stockpile 116 is reclaimed and conveyed to a weighing and proportioning unit 118. In this unit, the base mix and other trimming materials such as fluxes, solid fuel, return fines and additives are continuously withdrawn from stock bins in predetermined proportions and fed to a rotating granulation drum 120. Additives such as calcined lime are added to improve the quality of the wet agglomerate. In the granulation drum, water is added continuously at a pre-determined flow rate to facilitate wet agglomeration, i.e., mixing and nodulizing of all the raw materials. The output from the granulation drum is green mix that has a narrower particle size distribution compared to that of the feed mix to the drum. The green mix are further subjected to a thermal agglomeration process. The thermal agglomeration, known as sintering, is carried out in a long horizontal moving strand 122 consisting of pallet cars equipped with grate bars at the bottom. The green mix in continuously charged on the pallet cars of the moving strand at a predetermined flow rate and up to a predetermined bed height using a charging device, typically a rolling feed drum. After the green mix is charged, the top portion of the bed is ignited at high temperatures (>1100 oC) to initiate combustion of the solid fuel present in the green mix. Suction is continuously applied across the height of the bed using a waste gas fan leading to flow of air along the height of the bed. The flow air facilitates combustion of fuel in the green mix in the moving strand. During the thermal agglomeration process, the green mix undergo thermal-chemical processes such as drying of moisture, combustion, calcination of fluxes, melting and solidification. The energy required for the thermal agglomeration process is supplied from the combustion of solid fuel. The output from the thermal agglomeration unit is a sinter cake at high temperature. The sinter cake is crushed in a spike crusher 130 and the crushed sinter chunks are air-cooled in an annual cooler 132. The size of cooled sinter chunks is further reduced to typically less than 40 mm in a double roll crusher 134. The output from the double roll crusher is screened remove undersized sinter (typically less than 5-6 mm) that is recycled, hearth layer (typically 10-25 mm) that is used in the sinter strand and product sinter (typically 5-40 mm) that is transported to the subsequent metal extraction process. The flue/waste gas from the thermal agglomeration unit (sinter strand) is cleaned using bag filters or electrostatic precipitators (ESPs) to remove fine dust particles. The cleaned flue gas is vented from the stack. The process variables related to the granulation operation such as base mix flow rate, fuel flow rate, flux flow rate, binder flow rate, water flow rate, feed composition and size distribution from laboratory measurement, and process variables related to the sinter strand such as strand speed, suction pressure, firing/ignition temperature, bed height, etc. are fed to the programmable logic controller (PLC) or distributed control system (DCS) and SCADA to control the plant. Agglomeration of ores is also carried out in pelletization plants via a process called pelletization. This process is suitable for ore fines less than 150 microns in size. The pelletization plant consists of a mixing and blending unit where raw materials such as iron ore fines, fluxes and solid fuel are thoroughly mixed in predetermined proportions. If the size of raw materials is not in the desired range (typically less than 150 microns), size reduction may be carried out in a grinding circuit. The feed mix is continuously fed to a balling disc or drum where water is added at a predetermined flow rate to facilitate the growth of green balls. The green balls or pellets are discharged from the balling disc and charged up to a certain height using a charging device into an induration furnace that consists of a moving strand pallet cars equipped with grate bars at the bottom. In the induration process, the green balls experience various thermo-physical phenomena such as drying, calcination, combustion, melting and solidification, fusion bonding and cooling. The energy required for induration of pellets is supplied externally via a high temperature flue gas generated by combustion of fuels such as natural gas or coal tar. The heat-hardened pellets from the induration furnace are screened to remove undersized material and product pellets (typically 9 to 16 mm in size) are transported to the subsequent metal extraction process. In addition, the agglomeration plant 102 consist of a plurality of key sensors such as a moisture sensor 124, a particle size analyzer 126 and a wireless bed temperature sensor 128. The moisture sensor 124 is configured to measure real-time water/moisture content of the wet agglomerates. The particle size analyzer 126 is configured to provide real-time size distribution of wet agglomerates. The wireless bed temperature sensor 128 is configured to provide real-time temperature at different heights and lengths of the thermal agglomeration unit. According to an embodiment of the disclosure, a block diagram of the system 100 for optimization of the agglomeration plant 102 is shown in FIG. 1. The system 100 comprises a plurality of modules for performing various functions. The plurality of modules work in combination for real-time monitoring and optimization of the ore agglomeration plant 102. The system 100 comprises a plurality of agglomeration plant data sources 136, an agglomeration plant automation system 138 or distributed control system (DCS) 138, a server 140, a real-time monitoring and process optimization (RTMO) module 142, a model repository 144, a knowledge database 146, a plurality of databases 148 and the I/O interface 106 of FIG. 2. It should be appreciated that the model repository 144, the knowledge database 146 and the plurality of databases 148 could be the part of the data repository 114 of FIG. 2. In the preferred embodiment, the distributed control system 138 or the agglomeration plant automation system 138 operates the agglomeration plant 102 in a prescribed manner such that the agglomeration plant 102 meets the required throughput demand from the subsequent metal extraction process while keeping operations safe and optimal in terms of agglomerate yield and overall fuel consumption, and quality of agglomerates and emissions from the plant being within prescribed limits. The agglomeration plant automation system 138 interacts with various respective agglomeration data sources 136 which comprises of a historian, manufacturing execution system (MES) and a laboratory information management system (LIMS), and saves the real-time data within these data sources. The agglomeration plant automation system 138 also interacts with the real-time monitoring and process optimization (RTMO) module 142 through the server 140 such as an OPC server. The real-time monitoring and process optimization module 142 receives real-time data from the agglomeration plant automation system 138 via the server 140, the real-time and non-real-time data from the plurality of agglomeration plant data sources 136, and other relevant information from the plurality of databases 148, the knowledge database 146 and the model repository 144. According to an embodiment of the disclosure, referring to FIG. 1, the knowledge database 146 constitutes process knowledge and user knowledge derived from one or more modules of the real-time process optimization module 142. It comprises knowledge derived from multitude of simulations performed by the offline simulation module, knowledge of influence of various raw materials on the agglomeration plant, performance information of the plurality of physics-based and data-driven models of the agglomeration plant, and diagnostics information or fault trees for common process and equipment in the plant. The knowledge database is used by a plurality of modules of the real-time optimization module. According to an embodiment of the disclosure, referring to FIG. 1, the plurality of databases 148 comprise static and dynamic information pertaining to the agglomeration plant. The databases comprise a material database that contains static properties of raw materials, intermediate products, byproducts, final product and emissions, etc., an equipment database that contains equipment design data, details of construction materials, etc., a process configuration database that contains of process flowsheets, equipment layout, control and instrumentation diagrams, etc., an algorithm databases that contains algorithms and techniques of data-driven and physics-based models, and solvers for physics-based models and optimization problems. The databases further comprise an operations database that contains sensor data, a laboratory database that contains of properties of raw materials, intermediate products, byproducts, final products and emissions obtained via tests at the laboratories, a maintenance database that consists of condition of the process, health of the equipment, maintenance records indicating corrective or remedial actions on various equipment, etc., an environment database that consists of weather and climate data such as ambient temperature, atmospheric pressure, humidity, etc. According to an embodiment of the disclosure, referring to FIG. 1, the model repository 144 comprises physics-based models, data-driven models, soft sensor models and configured optimization models of the agglomeration plant. According to an embodiment of the disclosure, the real-time monitoring and process optimization module 142 comprises a plurality of modules. The plurality of modules comprises a receiving module 150, a data preprocessing module 152, a soft sensor module 154, an offline simulation module 156, a prediction module 158, a self-learning module 160 and an optimization module 162. The receiving module 150 is configured to receive the plurality of real-time data from the server 140 and real-time and non-real-time data from the agglomeration plant data sources 136 at a pre-determined frequency as an input. Data may be configured to be received at a frequency of once in every 1 min, once in every 5 min, etc. Real-time data comprises operations data such as temperatures, pressures, flow rates, levels, valve opening percentages, vibrations, chemical composition of gases, dust levels, power consumption, motor currents, motor RPM, etc. measured in different units of the agglomeration unit such as the weighing and proportioning unit, the mixing and blending unit, the wet agglomeration unit, the charging device, the thermal agglomeration unit, the cooling unit, the screening and sizing unit, and the gas cleaning unit. It also comprises environment data such as ambient temperature, atmospheric pressure, ambient humidity, rainfall, etc. The non-real-time includes data from laboratory tests and maintenance activities. Laboratory data consists of chemical composition, particle size distribution, density and microstructure information of raw materials, wet agglomerates and agglomerates. It also comprises results from quality tests such as tumbler index, abrasion index cold compressive strength, reduction degradation index, reducibility index and softening-melting conducted on agglomerates. The maintenance data includes details of planned and unplanned maintenance activities performed on one or more units of the plant, and condition and health of the process and various units in the plant. Real-time data is obtained from plant automation systems such as distributed control system (DCS) via a communication server such as OPC server or via an operations data source such as a historian. The non-real-time data is obtained from LIMS, MES, historian and other plant maintenance databases. In a typical agglomeration plant, the total number of variables from various data sources can be between 300 and 600. The data preprocessing module 152 is configured to pre-process the received data. The preprocessing of data comprises identification and removal of outliers, imputation of missing data, and synchronization and integration of a plurality of variables from one or more data sources using the residence time of all the units of the agglomeration plant. The sampling frequency of real-time and non-real-time data may be unified to, for example, once every 1 min, where the real-time data is averaged as necessary and the non-real-time data is interpolated or replicated as necessary. The soft sensor module 154 is configured to obtain simulated data that is not generated by the physical sensors of the plant. The module uses the pre-processed data and a plurality of soft sensors to generate simulated data. The soft sensor module 154 comprises physics-based and data-driven soft sensors comprising of flow rates of input feed materials to the agglomeration plant, size distribution of input feed mix, mean diameter of input feed mix, chemical composition of input feed mix and moisture content of input feed mix. The module is further configured to combine simulated data and pre-processed data to obtain integrated data. The integrated data is further used to provide services such as prediction, process optimization, continuous monitoring and self-learning as explained in the later part of the disclosure. According to an embodiment of the disclosure, the offline simulation module 156 performs simulation tasks on the agglomeration plant 102 that are not required or not possible in real-time owing to the complexity of the system but are useful to be performed at a regular intervals. The offline simulation module 156 generates specific test instances for simulation that are simulated using high fidelity physics-based models and data-driven models. These modules provides insights into overall operation of the agglomeration plant 102. Simulation from offline simulation module may be requested by the prediction module, the process optimization module or the self-learning module. The offline simulation module interacts with the plurality of databases 148, the knowledge database 146 and the model repository 144. The information processed by the offline simulation module 156 is stored in the plurality of databases 148. According to an embodiment of the disclosure, a block diagram of the prediction module 158 is shown in the FIG. 4. The prediction module 158 further comprises a blending/mixing module 402, a wet agglomeration module 404, a thermal agglomeration module 406, a charging module 408 and a plant KPI module 410. The prediction module 158 is also in communication with the user interface 106, the plurality of databases 148, the knowledge database 146, the agglomeration plant data sources 136, the self-learning module 160, the offline simulation module 156 and the optimization module 162. According to an embodiment of the disclosure, the blending/mixing module 402 is configured to predict the chemical composition, particle size distribution and moisture/water content of the feed mix given the flow rates or proportion in which the raw materials are mixed. The raw materials comprise ore fines, solid fuel, fluxes, return fines, additives, solid wastes, etc. The chemical composition comprises metallic species such as Fe, Mn, Zn, Pb, etc. and oxide species such as FeOx, MnOx, ZnOx, PbOx, CaO, SiO2, MgO, Al2O3, Cr2O3, etc. and carbon. According to an embodiment of the disclosure, the wet agglomeration module 404 is configured to determine a first set of parameters using a physics-based and data-driven wet agglomeration models and the integrated data. The wet agglomeration model comprises algebraic equations representing the mixing and particle layering process taking place inside the wet agglomeration unit and could be a population balance model. The first set of parameters comprises size distribution, mean diameter, water content, D50, D80 and granulation index of the wet agglomerate. The wet agglomerate refers to green mix in case of sintering and green balls in case of pelletization. According to an embodiment of the disclosure, the charging module 408 is configured to determine a second set of parameters using physics-based and data-driven charging models, the first set of parameters and the integrated data. The physics-based charging model comprises the relationship among the mean diameter of wet agglomerate, the height of wet agglomerate in the thermal agglomeration unit, pressure difference across the bed, velocity of air through the bed and voidage of the bed, and could be modified Ergun equation and Japanese Permeability equation, etc. The second set of parameters comprises voidage and permeability of the wet agglomerate bed, the velocity of air through the bed and the size and species segregation profile of bed. According to an embodiment of the disclosure, the thermal agglomeration module 406 is configured to determine a third set of parameters using a physics-based thermal agglomeration model, the first set of parameters, the second set of parameters and the integrated data. The thermal agglomeration model comprises nonlinear differential and algebraic equations representing the various physical-chemical phenomena and reactions occurring in the thermal agglomeration unit. The phenomena modeled by the thermal agglomeration model include evaporation and condensation of water, calcination of fluxes, combustion of solid fuel, Boudouard reaction, reduction of metallic oxides, re-oxidation of metallic oxides, melting and solidification. The third set of parameters comprises distributions of temperature and a plurality of chemical species at different heights of the bed and lengths of the thermal agglomeration unit, the velocity and flow rate of inlet air and gas at different lengths of the thermal agglomeration unit, temperature, velocity and flow rate of outlet gas from different lengths of the thermal agglomeration unit, the velocity and thickness of the flame front at different lengths of the thermal agglomeration unit, temperature and flow rate of the exhaust gas at different lengths of the thermal agglomeration unit, length and location of burn through point in the thermal agglomeration unit, and temperature of agglomerate discharged from the thermal agglomeration unit. The chemical species comprise metallic species such as Fe, Mn, Zn, Pb, etc. and oxide species such as FeOx, MnOx, ZnOx, PbOx, CaO, SiO2, MgO, Al2O3, Cr2O3, etc., carbon, liquid moisture and water vapor. Typical temperature profiles obtained from the thermal agglomeration model at different bed heights and along the length of the thermal agglomeration unit in a pelletization plant, i.e. induration furnace are depicted in FIG. 8. It can be observed that the agglomerates at the bottom of the bed experience lower temperatures compared to those at the top of the bed. According to an embodiment of the disclosure, the plant KPI module 410 is configured to determine a final set of parameters using a plurality of data-driven models, the first, the second and the third set of parameters, and the integrated data. The final set of parameters comprises productivity, yield, efficiency, fuel rate and percentage of undersized agglomerates from the agglomeration plant, and size distribution, mean diameter, tumbler index, abrasion index, cold compressive strength, reduction degradation index, reducibility index, and softening melting parameters of the agglomerate. It should be noted that the plurality of data-driven models in the wet agglomeration module, charging module and plant KPI module are built using machine learning and deep learning techniques that include variants of regression (multiple linear regression, stepwise regression, forward regression, backward regression, partial least squares regression, principal component regression, Gaussian process regression, polynomial regression, etc.), decision tree and its variants (random forest, bagging, boosting, bootstrapping), support vector regression, k-nearest neighbors regression, spline fitting or its variants (e.g. multi adaptive regression splines), artificial neural networks and it variants (multi-layer perceptron, recurrent neural networks & its variants e.g. long short term memory networks, and convolutional neural networks) and time series regression models. The models can be point models (that do not consider temporal relationship among data instances) or time series models (that consider temporal relationship among data instances). According to an embodiment of the disclosure a block diagram of the optimization module 162 is shown in FIG. 5. The optimization module 162 is configured to optimize a plurality of key performance parameters of the agglomeration plant 102 using the plurality of physics-based and data-driven models. The plurality of key performance parameters (KPI) of the agglomeration plant 102 comprises throughput, productivity, yield, efficiency, fuel rate and percentage of undersized agglomerates from the agglomeration plant, chemical composition, size distribution, mean diameter, tumbler index, abrasion index, cold compressive strength, reduction degradation index, reducibility index, and softening melting parameters of the agglomerate, granulation index and mean diameter of the wet agglomerate, location of burn through point and maximum wind-box temperature in the thermal agglomeration unit, temperature of waste gas entering the gas cleaning system, percentages of pollutants such as CO, NOx, SOx in the waste gas . The optimization module 162 further comprises an optimization configuration module 502, an optimization execution module 504 and a recommendation module 506. The optimization configuration module is configured to enable configuring of optimization models/optimizer specific to the agglomeration plant. The optimizer may be configured after a predefined time interval, when the key performance parameters of the agglomeration plant cross the predefined thresholds, or by manual intervention. Configuration of the optimization problem involves choosing the type of optimization problem (single objective vs multi objective), direction of optimization (maximize or minimize), one or more objective functions, one or more constraints and their lower and upper limits, one or more manipulated variables and their lower and upper limits, and one or more groups of manipulated variables. Inputs for configuring the optimization model may be taken from the user via the user interface 106 and the configured optimization models are stored in the model repository 144. The objective functions and constraint functions can be chosen from the plurality of key performance parameters of the agglomeration plant 102. They can also be derived from or be a combination of the plurality of key performance parameters of the plant. A sample optimization problem for the agglomeration plant 102 is: ?Objective Function1: max???(Productivity)? ?Objective Function2: max???(Tumbler Index)? Constraints ?RDI?^L